186 lines
5.1 KiB
Plaintext
186 lines
5.1 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "f74ce078-f7e8-4733-a14c-14d8815a3626",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-06T15:33:36.424263Z",
|
||
"start_time": "2025-04-06T15:33:36.048334Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import tushare as ts\n",
|
||
"ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
|
||
"pro = ts.pro_api()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "44dd8d87-e60b-49e5-aed9-efaa7f92d4fe",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-06T15:33:37.871314Z",
|
||
"start_time": "2025-04-06T15:33:36.424263Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" ts_code trade_date\n",
|
||
"0 801001.SI 20250221\n",
|
||
"1 801002.SI 20250221\n",
|
||
"2 801003.SI 20250221\n",
|
||
"3 801005.SI 20250221\n",
|
||
"4 801010.SI 20250221\n",
|
||
"... ... ...\n",
|
||
"1751 859811.SI 20250401\n",
|
||
"1752 859821.SI 20250401\n",
|
||
"1753 859822.SI 20250401\n",
|
||
"1754 859852.SI 20250401\n",
|
||
"1755 859951.SI 20250401\n",
|
||
"\n",
|
||
"[1057124 rows x 2 columns]\n",
|
||
"20250403\n",
|
||
"start_date: 20250407\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import time\n",
|
||
"\n",
|
||
"h5_filename = '../../../data/sw_daily.h5'\n",
|
||
"key = '/sw_daily'\n",
|
||
"max_date = None\n",
|
||
"with pd.HDFStore(h5_filename, mode='r') as store:\n",
|
||
" df = store[key][['ts_code', 'trade_date']]\n",
|
||
" print(df)\n",
|
||
" max_date = df['trade_date'].max()\n",
|
||
"\n",
|
||
"print(max_date)\n",
|
||
"trade_cal = pro.trade_cal(exchange='', start_date='20170101', end_date='20250420')\n",
|
||
"trade_cal = trade_cal[trade_cal['is_open'] == 1] # 只保留交易日\n",
|
||
"trade_dates = trade_cal[trade_cal['cal_date'] > max_date]['cal_date'].tolist()\n",
|
||
"start_date = min(trade_dates)\n",
|
||
"print(f'start_date: {start_date}')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "747acc47-0884-4f76-90fb-276f6494e31d",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-06T15:33:40.123037Z",
|
||
"start_time": "2025-04-06T15:33:37.881433Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"任务 20250417 完成\n",
|
||
"任务 20250418 完成\n",
|
||
"任务 20250416 完成\n",
|
||
"任务 20250415 完成\n",
|
||
"任务 20250414 完成\n",
|
||
"任务 20250411 完成\n",
|
||
"任务 20250409 完成\n",
|
||
"任务 20250410 完成\n",
|
||
"任务 20250408 完成\n",
|
||
"任务 20250407 完成\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from concurrent.futures import ThreadPoolExecutor, as_completed\n",
|
||
"\n",
|
||
"all_daily_data = []\n",
|
||
"\n",
|
||
"# API 调用计数和时间控制变量\n",
|
||
"api_call_count = 0\n",
|
||
"batch_start_time = time.time()\n",
|
||
"\n",
|
||
"\n",
|
||
"def get_data(trade_date):\n",
|
||
" time.sleep(0.1)\n",
|
||
" data = pro.sw_daily(trade_date=trade_date)\n",
|
||
" if data is not None and not data.empty:\n",
|
||
" return data\n",
|
||
"\n",
|
||
"\n",
|
||
"with ThreadPoolExecutor(max_workers=2) as executor:\n",
|
||
" future_to_date = {executor.submit(get_data, td): td for td in trade_dates}\n",
|
||
"\n",
|
||
" for future in as_completed(future_to_date):\n",
|
||
" trade_date = future_to_date[future] # 获取对应的交易日期\n",
|
||
" try:\n",
|
||
" result = future.result() # 获取任务执行的结果\n",
|
||
" all_daily_data.append(result)\n",
|
||
" print(f\"任务 {trade_date} 完成\")\n",
|
||
" except Exception as e:\n",
|
||
" print(f\"获取 {trade_date} 数据时出错: {e}\")\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "c6765638-481f-40d8-a259-2e7b25362618",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-06T15:33:40.286614Z",
|
||
"start_time": "2025-04-06T15:33:40.138227Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"所有每日基础数据获取并保存完毕！\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n",
|
||
"\n",
|
||
"# 将所有数据合并为一个 DataFrame\n",
|
||
"\n",
|
||
"# 将数据保存为 HDF5 文件（table 格式）\n",
|
||
"all_daily_data_df.to_hdf(h5_filename, key=key, mode='a', format='table', append=True, data_columns=True)\n",
|
||
"\n",
|
||
"print(\"所有每日基础数据获取并保存完毕！\")"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.11.11"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|